© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60267
    Prev
    Next
    INDEX
    Explanations

    signing verb or noun

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects occurrences of the word “sign.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     In
    -2.48
     –
    -2.45
     Houſe
    -2.19
    ࿙
    -2.19
     envelop
    -2.11
    CHREIB
    -2.06
     Also
    -2.05
     all
    -2.05
     More
    -2.02
     They
    -1.95
    POSITIVE LOGITS
    ຼ
    2.55
    𓐍
    2.45
    曾經
    2.39
    a
    2.38
    
    2.36
    ῞
    2.28
    ?」
    2.23
    禑
    2.22
    u
    2.19
    ᷆
    2.19
    Activations Density 0.007%

    No Known Activations